A model that try to replicate, let's say walking in the street (and seen others walk in the street) from First person PoV, sorry for the bad quality demo video, no time to finesse right now, read below for quick summary, i'll update/upgrade later.

Example prompt : str3etLIF3 video scene featuring a group of young people walking on the sidewalk in front of a night club, outdoor at night in a (well lit:0.7) city of Los Angeles, two women and two men are the main focus, they are walking toward the camera, one of the woman is a beautiful blonde wearing a fashion beige minidress form fitting outfit, she walk, and she is smoking vaping e-cigare, one man is holding his cellphone as he talk to someone else, one of the men is wearing a black pants, and the other main man is wearing a light blue jeans, (sports cars can be seen passing on the road left side:1.15) of the frame, dynamic, 4k ultra quality, color graded mastery. (detailed faces, detailed body shapes and body movements:1.25)

Or just start your prompt by str3etLIF3 and be creative, knowing that the model was trained on first person street walking, street 'chilling' footages, mostly of people walking on the sidewalk, and in particular pretty girls in the night life of big cities (no NSFW footage used, just some provocative outfit for some but that's all) there is also men in the training video, just less than women, so model probably will generate more females unless prompted accordingly

I have no time currently, since I'm barely able to stay awake as I write this, to make better example video (this one is quite bad, I try to lear a new workflow that for others is amazing, but for me it seems garbage, not the worflow, but my use of it :p) when I wake up in a few hours i'll start proper testing, I will eventually even change the model (this one I upload is epoch 40, the last, but I have a sneaky feeling epoch 30 is actually a touch better, anyway i'll see tomorrow no big deal, enjoy epoch 40 for now...)

try also if you want, combining it with my previouus lora Move_Enhancer at 0.6 or so (for Move_Enhancer) it may give decent result, or funny result

Again, seeya later, i'll make better demo more representative of the model capacity, and offer more example prompt have a good one.